Embedded Attention Network for Semantic Segmentation

Lv, Qingxuan; Feng, Mingzhe; Sun, Xin; Dong, Junyu; Chen, Changrui

doi:10.1109/lra.2021.3126892

Cited by 3 publications

(1 citation statement)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Sun et al [15] proposed Gaussian dynamic convolution, which can dynamically select sampling regions based on the offset of the Gaussian distribution, and they further constructed a lightweight network to handle the complex single-image segmentation task. Lv et al [16] introduced the embedded attention module to generate feature bases and continuously update them using contextual information to ensure accuracy while greatly reducing the computation and improving segmentation efficiency.…”

Section: General Semantic Segmentationmentioning

confidence: 99%

Gaussian Dynamic Convolution for Semantic Segmentation in Remote Sensing Images

et al. 2022

View full text Add to dashboard Cite

Different scales of the objects pose a great challenge for the segmentation of remote sensing images of special scenes. This paper focuses on the problem of large-scale variations of the target objects via a dynamical receptive field of the deep network. We construct a Gaussian dynamic convolution network by introducing a dynamic convolution layer to enhance remote sensing image understanding. Moreover, we propose a new Gaussian pyramid pooling (GPP) for multi-scale object segmentation. The proposed network can expand the size of the receptive field and improve its efficiency in aggregating contextual information. Experiments verify that our method outperforms the popular semantic segmentation methods on large remote sensing image datasets, including iSAID and LoveDA. Moreover, we conduct experiments to demonstrate that the Gaussian dynamic convolution works more effectively on remote sensing images than other convolutional layers.

show abstract

Section: General Semantic Segmentationmentioning

confidence: 99%